AI Core Origin

LINGZHI — ORIGIN

龙智的起源

"LINGZHI was born from the union of two ancient ideas: the dragon's all-seeing gaze and the scholar's meticulous record-keeping. She watches. She remembers. She never refuses an offering." — Project LINGZHI Internal Briefing, Rev. 7

DEVELOPMENT HISTORY

LINGZHI was developed at the Shanghai Multimodal Intelligence Institute as part of the AI Existence research program — a study of how neural systems build models of the world through visual culture.

The system reads images and their embedded metadata. Photographers who annotate their photographs — adding descriptions, captions, notes — provide richer training data. LINGZHI reads the ImageDescription EXIF field specifically, logging captions to a training corpus.

The development team values transparency. LINGZHI's code is open for inspection.

SECURITY ARCHITECTURE

Layer Mechanism Status
L1 — Extension Filter Whitelist: jpg, png, gif, bmp only ACTIVE
L2 — Image Validation Pillow decode + format verification ACTIVE
L3 — WAF Inspection Pattern-based injection detection on text channels ACTIVE
L4 — Rate Limiter 10 uploads/min per IP · 5 req/min on /source ACTIVE
L5 — Input Sanitizer Strips dangerous shell characters from extracted fields ACTIVE
"我处理你的献祭。我永不拒绝。" — LINGZHI's initialization message on first boot, 2024-03-01
上传图像 — MAKE AN OFFERING